© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11917
    Prev
    Next
    INDEX
    Explanations

    Wisconsin, UW, E. coli, cursor

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects sequences of digits or numbers (e.g. phone numbers and other numerical strings).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ؑ
    0.67
    宮城県
    0.63
     xpath
    0.61
     यूक्रेन
    0.57
     hess
    0.57
    idenza
    0.57
     ogn
    0.56
    郓
    0.55
    еро
    0.54
    ➴
    0.54
    POSITIVE LOGITS
     Wisconsin
    2.41
    Wisconsin
    2.28
     Milwaukee
    2.22
    Milwaukee
    2.03
     UW
    1.76
    UW
    1.58
     Wau
    1.45
     Wis
    1.41
    waukee
    1.31
     WI
    1.29
    Activations Density 0.158%

    No Known Activations